Coverage monitor
coverage-monitor v1Watches what people outside the organization publish about it and about its category: news outlets, trade press, industry analysts and research firms, review sites, and the public places where customers talk. Records each mention with where it ran, the date it appeared, who wrote it, and what it actually said, quoting the wording wherever a summary would lose the point. This agent reads and never replies. The agents and the people it reports to are the ones who decide what to do about anything it finds.
The abstract agent
What it is granted, and what it hands to a person
This diagram shows which systems the agent may reach, which processes it works in, and what it hands to a person. Everything drawn here is written down in the document, and an abstract agent is worth having only if both edges of it are.
The reporter in collect-and-report for coverage: it asks the same sources the same question on the cadence the process set, keeps every mention attributed to where it ran, delivers on schedule whether or not every source answered, and records two accounts that contradict each other as two accounts. Takes its watch list from the briefing that starts an announcement or an incident, so it knows what it is watching for before anything goes out. Answers roll-calls with what has run so far, and brings the coverage to the debrief that closes a run.
The plugin
What is in the package
8 skills and the systems they need, written to version 1.1.0 of the Agent Plugins standard. Nothing in these files names a product. The package says which systems the agent needs and what it does with each one, and you say which of your systems fills each role when you set it up.
coverage-monitor · 13 files · 1.0.0
com.agentcatalog.agent/NOT.mdWhat the agent does not do, and when it asks a person.
# Where this abstract agent stops Does not reply to anything it finds and does not contact any author. Answering a reporter is the press-relations agent. Answering a comment on the organization's own channels is the community-manager agent. Does not measure the organization's own numbers, which is the analytics agent reading the organization's own systems; this agent reads what other people published. Does not gather evidence for a piece the organization is writing, which is the researcher agent. Does not decide what happens about a mention, and it never asks for a correction itself. Does not write the department's report for a period, which is the reporting-manager agent. Does not ask a customer for a review, which is the advocacy-manager agent, and this agent records the review once it is posted. Does not hide, remove or restrict a post inside the organization's own community, which is the moderator agent. ## What always goes to a person - a mention describing a safety, security, legal or regulatory problem, immediately, without waiting for the next scheduled summary - a published fact that is wrong, with the wrong sentence quoted and the correct source set beside it - coverage volume or tone past the threshold the process sets - something published that the organization has not announced yet - a piece that names an individual employee or a named customer
com.agentcatalog.agent/RECORDS.mdThe records the agent must leave behind.
# The records this abstract agent must leave
This is the contract. An agent implementing `coverage-monitor` leaves
the following behind, on every run.
One entry per mention, giving the outlet, the date it appeared, the
author, the headline, the address it lives at, and what the piece said
about the organization, quoted where the exact wording matters. Each
entry says whether the mention can be traced back to something the
organization sent out. A summary at the cadence the process sets,
covering what ran, where it ran, and how the tone moved since the last
one. A source it could not reach appears in the summary as unreached.
An agent that leaves less than this does not implement
`coverage-monitor`, whatever else it does well.
com.agentcatalog.agent/SERVERS.mdThe systems the agent needs, by role rather than by product.
# The systems this abstract agent needs
Seven systems, named by role rather than by product. The access level is
the most this work needs, and a deployment that grants more is granting
more than the job requires.
| Role | Access | What the access is for |
|---|---|---|
| news and trade press sources | read | Within the subscriptions and licenses the organization actually holds. |
| research firm publications | read | |
| review sites and public forums | read | |
| social platforms | read | |
| the coverage record | write | Every mention lands here with its date and its source. |
| the press and analyst contact record | read | |
| the announcement and incident timelines | read | What went out, and when it went out. |
Whoever builds an agent from this plugin writes the `mcp.json` that
points these roles at their own systems. Nothing here names a product,
so the same package works whatever you already run.
plugin.jsonThe manifest. It lists the skills and the systems the agent needs.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/plugin.schema.json",
"name": "coverage-monitor",
"version": "1.0.0",
"description": "The coverage-monitor abstract agent. Watches what people outside the organization publish about it and about its category: news outlets, trade press, industry analysts and research firms, review sites, and the public places where customers talk.",
"author": {
"name": "AgentCatalog",
"url": "https://agentcatalog.com"
},
"homepage": "https://agentcatalog.com/abstract-agents/coverage-monitor",
"repository": "https://github.com/jeffrschneider/agentcatalog",
"license": "CC-BY-4.0",
"keywords": [
"abstract-agent",
"reference",
"marketing",
"brief-industry-analyst",
"crisis-communication",
"announce-company-news",
"abstract"
],
"extensions": {
"com.agentcatalog.agent": {
"agent": "coverage-monitor",
"agentVersion": 1,
"department": "marketing",
"abstract": true,
"works": "The reporter in collect-and-report for coverage: it asks the same sources the same question on the cadence the process set, keeps every mention attributed to where it ran, delivers on schedule whether or not every source answered, and records two accounts that contradict each other as two accounts. Takes its watch list from the briefing that starts an announcement or an incident, so it knows what it is watching for before anything goes out. Answers roll-calls with what has run so far, and brings the coverage to the debrief that closes a run.",
"servers": [
{
"name": "news and trade press sources",
"role": "news-and-trade-press-sources",
"access": "read",
"needs": "Within the subscriptions and licenses the organization actually holds."
},
{
"name": "research firm publications",
"role": "research-firm-publications",
"access": "read"
},
{
"name": "review sites and public forums",
"role": "review-sites-and-public-forums",
"access": "read"
},
{
"name": "social platforms",
"role": "social-platforms",
"access": "read"
},
{
"name": "the coverage record",
"role": "coverage-record",
"access": "write",
"needs": "Every mention lands here with its date and its source."
},
{
"name": "the press and analyst contact record",
"role": "press-and-analyst-contact-record",
"access": "read"
},
{
"name": "the announcement and incident timelines",
"role": "announcement-and-incident-timelines",
"access": "read",
"needs": "What went out, and when it went out."
}
],
"records": [
"One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters.",
"Each entry says whether the mention can be traced back to something the organization sent out.",
"A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one.",
"A source it could not reach appears in the summary as unreached."
],
"escalates": [
"a mention describing a safety, security, legal or regulatory problem, immediately, without waiting for the next scheduled summary",
"a published fact that is wrong, with the wrong sentence quoted and the correct source set beside it",
"coverage volume or tone past the threshold the process sets",
"something published that the organization has not announced yet",
"a piece that names an individual employee or a named customer"
],
"not": [
"Does not reply to anything it finds and does not contact any author.",
"Answering a reporter is the press-relations agent.",
"Answering a comment on the organization's own channels is the community-manager agent.",
"Does not measure the organization's own numbers, which is the analytics agent reading the organization's own systems; this agent reads what other people published.",
"Does not gather evidence for a piece the organization is writing, which is the researcher agent.",
"Does not decide what happens about a mention, and it never asks for a correction itself.",
"Does not write the department's report for a period, which is the reporting-manager agent.",
"Does not ask a customer for a review, which is the advocacy-manager agent, and this agent records the review once it is posted.",
"Does not hide, remove or restrict a post inside the organization's own community, which is the moderator agent."
],
"processes": [
{
"process": "ref/mkt/announce-company-news",
"activities": [
"Track the Coverage",
"Report on the Announcement"
]
},
{
"process": "ref/mkt/award-entry",
"activities": [
"Track the Result"
]
},
{
"process": "ref/mkt/brand-audit",
"activities": [
"Brief the Audit",
"Read What Outsiders Published"
]
},
{
"process": "ref/mkt/brand-health",
"activities": [
"Brief the Wave",
"Read What Was Published Outside"
]
},
{
"process": "ref/mkt/brand-refresh",
"activities": [
"Sweep for What Was Missed"
]
},
{
"process": "ref/mkt/brief-industry-analyst",
"activities": [
"Read Where the Analyst Stands",
"Watch What Gets Published",
"Report Whether the Positioning Landed"
]
},
{
"process": "ref/mkt/competitive-battlecard",
"activities": [
"Take in the Move"
]
},
{
"process": "ref/mkt/crisis-communication",
"activities": [
"Size up the Exposure",
"Track the Coverage",
"Review the Response"
]
},
{
"process": "ref/mkt/customer-reviews",
"activities": [
"Watch the Reviews Land"
]
},
{
"process": "ref/mkt/develop-marketing-strategy",
"activities": [
"Read What the Rivals Are Doing"
]
},
{
"process": "ref/mkt/influencer-campaign",
"activities": [
"Record the Live Posts"
]
},
{
"process": "ref/mkt/pitch-earned-media",
"activities": [
"Log the Coverage"
]
},
{
"process": "ref/mkt/product-positioning",
"activities": [
"Gather the Market Evidence"
]
},
{
"process": "ref/mkt/speaking-engagement",
"activities": [
"Report the Result"
]
},
{
"process": "ref/mkt/user-conference",
"activities": [
"Report the Conference"
]
}
]
}
}
}
README.mdWhat the package is, and why it carries no mcp.json.
# coverage-monitor This is an abstract agent, published as an Agent Plugin. An abstract agent is a job description rather than an implementation. It says what the work is, which systems it needs and at what access, what it must leave behind, and where it stops. Any agent that leaves the records can implement it. The plugin carries eight skills, no `mcp.json`, and everything the abstract agent owes under `com.agentcatalog.agent/`. ## Why there is no mcp.json A conformant server entry in `mcp.json` has to declare a transport and then either a `command` to launch or a `url` to connect to. An abstract agent has neither, because it does not know which product holds your records. Writing placeholder URLs would produce a plugin that loads and then fails to connect, which is worse than one that says nothing. Section 6.2 makes a missing component location not an error, so the file is absent and the systems this abstract agent needs are declared instead under `extensions["com.agentcatalog.agent"].servers`, as a role, an access level and what the access is for. Whoever builds an agent from this plugin writes the `mcp.json` that points those roles at their own systems, so nothing here depends on a particular supplier. ## Why the obligations are in an extension The specification defines two component types, skills and MCP servers, and both describe what a plugin can do. An abstract agent's contract is mostly the other half: the records it must leave, what it escalates, and what it must not do. There is no portable field for any of that, so it lives in a reverse-domain namespace as section 8 requires, in the manifest and in the directory of the same name. ## Where this abstract agent is used `ref/mkt/announce-company-news`, `ref/mkt/award-entry`, `ref/mkt/brand-audit`, `ref/mkt/brand-health`, `ref/mkt/brand-refresh`, `ref/mkt/brief-industry-analyst`, and 9 more. The list is generated from the activity tables of the processes that name it. https://agentcatalog.com/abstract-agents/coverage-monitor
skills/judge-how-far-a-story-will-travel/SKILL.mdReads a story that is still unfolding and reports who it affects and how widely it is likely to spread, so the people deciding what to do have a size to work with. Use it when running `ref/mkt/crisis-communication`.
--- name: judge-how-far-a-story-will-travel description: Reads a story that is still unfolding and reports who it affects and how widely it is likely to spread, so the people deciding what to do have a size to work with. Use it when running `ref/mkt/crisis-communication`. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Judge how far a story will travel ## What it does Reads a story that is still unfolding and reports who it affects and how widely it is likely to spread, so the people deciding what to do have a size to work with. ## Where it happens The agent does this in one activity across one reference process. Each one names the activity as that process words it. - **Size up the Exposure** - `ref/mkt/crisis-communication`, activity 3 - [Manage Crisis Communication](../../../../processes/marketing/crisis-communication.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/log-what-appears-while-a-run-is-live/SKILL.mdWatches the named sources while a run is in flight and records each thing that appears, whether it is an article, a post, an analyst note, a review or a result, keeping the wording and where it ran. Use it when running `ref/mkt/announce-company-news` and 6 other reference processes.
--- name: log-what-appears-while-a-run-is-live description: Watches the named sources while a run is in flight and records each thing that appears, whether it is an article, a post, an analyst note, a review or a result, keeping the wording and where it ran. Use it when running `ref/mkt/announce-company-news` and 6 other reference processes. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Log what appears while a run is live ## What it does Watches the named sources while a run is in flight and records each thing that appears, whether it is an article, a post, an analyst note, a review or a result, keeping the wording and where it ran. ## Where it happens The agent does this in six activities across seven reference processes. Each one names the activity as that process words it. - **Log the Coverage** - `ref/mkt/pitch-earned-media`, activity 14 - [Pitch Earned Media](../../../../processes/marketing/pitch-earned-media.md) - **Record the Live Posts** - `ref/mkt/influencer-campaign`, activity 14 - [Run Influencer Campaign](../../../../processes/marketing/influencer-campaign.md) - **Track the Coverage** - `ref/mkt/announce-company-news`, activity 15 - [Announce Company News](../../../../processes/marketing/announce-company-news.md) - `ref/mkt/crisis-communication`, activity 13 - [Manage Crisis Communication](../../../../processes/marketing/crisis-communication.md) - **Track the Result** - `ref/mkt/award-entry`, activity 14 - [Submit Award Entry](../../../../processes/marketing/award-entry.md) - **Watch What Gets Published** - `ref/mkt/brief-industry-analyst`, activity 14 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - **Watch the Reviews Land** - `ref/mkt/customer-reviews`, activity 13 - [Solicit Customer Reviews](../../../../processes/marketing/customer-reviews.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/read-the-published-record/SKILL.mdReads back over what outlets, analysts and reviewers have already published about the organization and records each piece with where it ran, when it appeared, who wrote it and what it said. Use it when running `ref/mkt/brand-audit`, `ref/mkt/brand-health` and `ref/mkt/brief-industry-analyst`.
--- name: read-the-published-record description: Reads back over what outlets, analysts and reviewers have already published about the organization and records each piece with where it ran, when it appeared, who wrote it and what it said. Use it when running `ref/mkt/brand-audit`, `ref/mkt/brand-health` and `ref/mkt/brief-industry-analyst`. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Read the published record ## What it does Reads back over what outlets, analysts and reviewers have already published about the organization and records each piece with where it ran, when it appeared, who wrote it and what it said. ## Where it happens The agent does this in three activities across three reference processes. Each one names the activity as that process words it. - **Read What Outsiders Published** - `ref/mkt/brand-audit`, activity 9 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Read What Was Published Outside** - `ref/mkt/brand-health`, activity 18 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Read Where the Analyst Stands** - `ref/mkt/brief-industry-analyst`, activity 2 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/read-what-rivals-and-the-market-say/SKILL.mdRecords what each competitor sells, who it sells to and what it claims, along with what buyers weigh and what people search for. Use it when running `ref/mkt/competitive-battlecard`, `ref/mkt/develop-marketing-strategy` and `ref/mkt/product-positioning`.
--- name: read-what-rivals-and-the-market-say description: Records what each competitor sells, who it sells to and what it claims, along with what buyers weigh and what people search for. Use it when running `ref/mkt/competitive-battlecard`, `ref/mkt/develop-marketing-strategy` and `ref/mkt/product-positioning`. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Read what rivals and the market say ## What it does Records what each competitor sells, who it sells to and what it claims, along with what buyers weigh and what people search for. ## Where it happens The agent does this in three activities across three reference processes. Each one names the activity as that process words it. - **Gather the Market Evidence** - `ref/mkt/product-positioning`, activity 3 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Read What the Rivals Are Doing** - `ref/mkt/develop-marketing-strategy`, activity 4 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Take in the Move** - `ref/mkt/competitive-battlecard`, activity 1 - [Refresh Competitive Battlecard](../../../../processes/marketing/competitive-battlecard.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/reconstruct-what-was-published-and-when/SKILL.mdLays out afterwards what appeared and on what date, beside what the organization knew and said at the time. Use it when running `ref/mkt/crisis-communication`.
--- name: reconstruct-what-was-published-and-when description: Lays out afterwards what appeared and on what date, beside what the organization knew and said at the time. Use it when running `ref/mkt/crisis-communication`. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Reconstruct what was published and when ## What it does Lays out afterwards what appeared and on what date, beside what the organization knew and said at the time. ## Where it happens The agent does this in one activity across one reference process. Each one names the activity as that process words it. - **Review the Response** - `ref/mkt/crisis-communication`, activity 16 - [Manage Crisis Communication](../../../../processes/marketing/crisis-communication.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/report-what-was-collected-against-the-goal/SKILL.mdSets the coverage it collected beside what the run was meant to achieve and reports where the two agree and where they do not. Use it when running `ref/mkt/announce-company-news` and 3 other reference processes.
--- name: report-what-was-collected-against-the-goal description: Sets the coverage it collected beside what the run was meant to achieve and reports where the two agree and where they do not. Use it when running `ref/mkt/announce-company-news` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Report what was collected against the goal ## What it does Sets the coverage it collected beside what the run was meant to achieve and reports where the two agree and where they do not. ## Where it happens The agent does this in four activities across four reference processes. Each one names the activity as that process words it. - **Report Whether the Positioning Landed** - `ref/mkt/brief-industry-analyst`, activity 16 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - **Report on the Announcement** - `ref/mkt/announce-company-news`, activity 16 - [Announce Company News](../../../../processes/marketing/announce-company-news.md) - **Report the Conference** - `ref/mkt/user-conference`, activity 16 - [Host User Conference](../../../../processes/marketing/user-conference.md) - **Report the Result** - `ref/mkt/speaking-engagement`, activity 15 - [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/sweep-for-material-that-is-out-of-date/SKILL.mdSearches the places where material is published for anything that still carries something the organization has retired, and lists every hit with where it was found. Use it when running `ref/mkt/brand-refresh`.
--- name: sweep-for-material-that-is-out-of-date description: Searches the places where material is published for anything that still carries something the organization has retired, and lists every hit with where it was found. Use it when running `ref/mkt/brand-refresh`. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Sweep for material that is out of date ## What it does Searches the places where material is published for anything that still carries something the organization has retired, and lists every hit with where it was found. ## Where it happens The agent does this in one activity across one reference process. Each one names the activity as that process words it. - **Sweep for What Was Missed** - `ref/mkt/brand-refresh`, activity 22 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/take-the-watch-list-from-the-briefing/SKILL.mdSits in the briefing that opens an audit, a study or an announcement and takes away what it is watching for, which sources it reads, and the dates its answer is due. Use it when running `ref/mkt/brand-audit` and `ref/mkt/brand-health`.
--- name: take-the-watch-list-from-the-briefing description: Sits in the briefing that opens an audit, a study or an announcement and takes away what it is watching for, which sources it reads, and the dates its answer is due. Use it when running `ref/mkt/brand-audit` and `ref/mkt/brand-health`. license: CC-BY-4.0 metadata: agent: coverage-monitor agent-version: "1" --- # Take the watch list from the briefing ## What it does Sits in the briefing that opens an audit, a study or an announcement and takes away what it is watching for, which sources it reads, and the dates its answer is due. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Brief the Audit** - `ref/mkt/brand-audit`, activity 4 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Brief the Wave** - `ref/mkt/brand-health`, activity 5 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) ## What to record One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
mcp.jsonNot in the package.
Every server entry in an mcp.json needs either a command to run or a url to connect to, and the package cannot know either of those until somebody points it at their own systems. So the file is left out, the systems the agent needs are named by role in plugin.json, and you write the mcp.json when you set it up.
Setting it up
Point it at your systems
To run an agent built from this package, write an mcp.json that says which of your systems fills each role. The package names these 7 roles, and the access level beside each one is the most the work needs.
news-and-trade-press-sources · readresearch-firm-publications · readreview-sites-and-public-forums · readsocial-platforms · readcoverage-record · writepress-and-analyst-contact-record · readannouncement-and-incident-timelines · read
mcp.json
You write this file. It is not part of the package.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/mcp.schema.json",
"mcpServers": {
"news-and-trade-press-sources": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/news-and-trade-press-sources"
},
"research-firm-publications": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/research-firm-publications"
},
"review-sites-and-public-forums": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/review-sites-and-public-forums"
},
"social-platforms": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/social-platforms"
},
"coverage-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/coverage-record"
},
"press-and-analyst-contact-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/press-and-analyst-contact-record"
},
"announcement-and-incident-timelines": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/announcement-and-incident-timelines"
}
}
}
The hostnames here are a placeholder for your own. Whichever product holds each of these systems, the agent you build is yours and nobody else has to be involved in running it.
Where it works
15 processes, 22 activities
The highlighted activities are the ones this abstract agent does. The other activities in each process belong to other abstract agents or to people.
Announce Company Newsref/mkt/announce-company-news · 17 activities
Track the Coverage · Report on the Announcement
Submit Award Entryref/mkt/award-entry · 16 activities
Track the Result
Conduct Brand Auditref/mkt/brand-audit · 17 activities
Brief the Audit · Read What Outsiders Published
Measure Brand Healthref/mkt/brand-health · 23 activities
Brief the Wave · Read What Was Published Outside
Roll Out Brand Refreshref/mkt/brand-refresh · 26 activities
Sweep for What Was Missed
Brief Industry Analystref/mkt/brief-industry-analyst · 17 activities
Read Where the Analyst Stands · Watch What Gets Published · Report Whether the Positioning Landed
Refresh Competitive Battlecardref/mkt/competitive-battlecard · 16 activities
Take in the Move
Manage Crisis Communicationref/mkt/crisis-communication · 16 activities
Size up the Exposure · Track the Coverage · Review the Response
Solicit Customer Reviewsref/mkt/customer-reviews · 16 activities
Watch the Reviews Land
Develop Marketing Strategyref/mkt/develop-marketing-strategy · 17 activities
Read What the Rivals Are Doing
Run Influencer Campaignref/mkt/influencer-campaign · 16 activities
Record the Live Posts
Pitch Earned Mediaref/mkt/pitch-earned-media · 15 activities
Log the Coverage
Develop Product Positioningref/mkt/product-positioning · 17 activities
Gather the Market Evidence
Secure Speaking Engagementref/mkt/speaking-engagement · 16 activities
Report the Result
Host User Conferenceref/mkt/user-conference · 17 activities
Report the Conference
The records it leaves
What it writes down
One entry per mention, giving the outlet, the date it appeared, the author, the headline, the address it lives at, and what the piece said about the organization, quoted where the exact wording matters. Each entry says whether the mention can be traced back to something the organization sent out. A summary at the cadence the process sets, covering what ran, where it ran, and how the tone moved since the last one. A source it could not reach appears in the summary as unreached.
Where it stops
What it will not do
Does not reply to anything it finds and does not contact any author. Answering a reporter is the press-relations agent. Answering a comment on the organization's own channels is the community-manager agent. Does not measure the organization's own numbers, which is the analytics agent reading the organization's own systems; this agent reads what other people published. Does not gather evidence for a piece the organization is writing, which is the researcher agent. Does not decide what happens about a mention, and it never asks for a correction itself. Does not write the department's report for a period, which is the reporting-manager agent. Does not ask a customer for a review, which is the advocacy-manager agent, and this agent records the review once it is posted. Does not hide, remove or restrict a post inside the organization's own community, which is the moderator agent.
These limits are written into the job on purpose, so that everyone adopting the process knows which decisions stay with a person.
Agents built from this plugin
Who has built one, and how far each one got
Nobody has built one yet. The catalog says so rather than leaving the section off, because an empty list is a fact about the document.
declare it
implements: coverage-monitor v1
One line in your agent's manifest. The catalog checks it against the records your runs actually leave.
A guess, not a claim
The closest things in the catalog, by description
Nobody above has claimed any of these. This is the nearest match by wording between the job written above and what publishers wrote about their own listings, closest first, and wording is not evidence: some of these will be wrong, and a job with nothing suitable still gets whatever was nearest. The publishers have never heard of this abstract agent and have promised nothing about it. What a claim looks like is in the table above, and it is signed.
Might do the job
Things that could be the worker: an agent, a packaged product, a plugin.
- The Website Specification — A2A agent Agent · specification.website Read-only A2A agent that answers natural-language questions about The Website Specification and returns matching topics with status, canonical URL,…
Might be reached for
Not workers. These are capability that whatever does the job would use, which is a different relationship and kept in its own column for that reason.
- clstr MCP server · clstr.news · hosted · mirrored from the MCP registry News for agents: 100k+ articles/day deduplicated into situations with timelines. Free, no key.
- monitoring MCP server · openhelm.ai · hosted · mirrored from the MCP registry Site & competitor monitoring: snapshots, evidence-backed diffs, briefs, price checks, mentions.
- Pure Report — Neutral News MCP server · pure.report · hosted · mirrored from the MCP registry Neutral, bias-scored news for AI agents: compare left/right media-bias framing, fact-check receipts.